Machine Learning Techniques for Pose Based Human Activity Recognition

Activity recognition is the task of identifying human actions and physical activities. It can have applications in broad areas including medical, sports and fitness, healthcare, behaviour analysis and security. Activity recognition is a widely sought after area of research in both Machine Learning (ML) and smart devices. The activity recognition plays an important role in the field of machine learning. There are several machine learning techniques which can be applied for pose based activity recognition. These techniques involve training machine learning models for the dataset. The dataset is obtained by using OpenPose framework. This framework provides keypoints from an input image. These keypoints represent the raw data determining the pose of a human. The machine learning model can predict the pose after training on the dataset. models